Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914886164938752 |
|---|---|
| author | Jeon, Jaehyeong Kim, Kibum Yoon, Kanghoon Park, Chanyoung |
| author_facet | Jeon, Jaehyeong Kim, Kibum Yoon, Kanghoon Park, Chanyoung |
| contents | The scene graph generation (SGG) task involves detecting objects within an image and predicting predicates that represent the relationships between the objects. However, in SGG benchmark datasets, each subject-object pair is annotated with a single predicate even though a single predicate may exhibit diverse semantics (i.e., semantic diversity), existing SGG models are trained to predict the one and only predicate for each pair. This in turn results in the SGG models to overlook the semantic diversity that may exist in a predicate, thus leading to biased predictions. In this paper, we propose a novel model-agnostic Semantic Diversity-aware Prototype-based Learning (DPL) framework that enables unbiased predictions based on the understanding of the semantic diversity of predicates. Specifically, DPL learns the regions in the semantic space covered by each predicate to distinguish among the various different semantics that a single predicate can represent. Extensive experiments demonstrate that our proposed model-agnostic DPL framework brings significant performance improvement on existing SGG models, and also effectively understands the semantic diversity of predicates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15396 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation Jeon, Jaehyeong Kim, Kibum Yoon, Kanghoon Park, Chanyoung Computer Vision and Pattern Recognition Artificial Intelligence The scene graph generation (SGG) task involves detecting objects within an image and predicting predicates that represent the relationships between the objects. However, in SGG benchmark datasets, each subject-object pair is annotated with a single predicate even though a single predicate may exhibit diverse semantics (i.e., semantic diversity), existing SGG models are trained to predict the one and only predicate for each pair. This in turn results in the SGG models to overlook the semantic diversity that may exist in a predicate, thus leading to biased predictions. In this paper, we propose a novel model-agnostic Semantic Diversity-aware Prototype-based Learning (DPL) framework that enables unbiased predictions based on the understanding of the semantic diversity of predicates. Specifically, DPL learns the regions in the semantic space covered by each predicate to distinguish among the various different semantics that a single predicate can represent. Extensive experiments demonstrate that our proposed model-agnostic DPL framework brings significant performance improvement on existing SGG models, and also effectively understands the semantic diversity of predicates. |
| title | Semantic Diversity-aware Prototype-based Learning for Unbiased Scene Graph Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2407.15396 |